linkedin-marketing
VerifiedPlan, draft, audit, and publish LinkedIn posts and comments. Use when the user wants to write a viral LinkedIn post, draft a comment or reply on any LinkedIn post URL, audit a draft against 2026 algorithm heuristics, remove AI tells, extract hook formulas from viral posts, or plan a week of content. Powered by the Publora API for publishing. User provides post/comment URLs, skill drafts content, user approves, then publishes.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 13.7 KB |
| assets/icon.svg | other | 768 B |
| assets/linkedin-skills-hero.png | binary | 793.6 KB |
| references/algorithm-heuristics.md | markdown | 8.4 KB |
| references/engagement-metrics-taxonomy.md | markdown | 2.6 KB |
| references/founder-topics.md | markdown | 14.2 KB |
| references/hook-formulas.md | markdown | 39.5 KB |
| references/industry-benchmarks.md | markdown | 4.2 KB |
| references/mcp-read-layer.md | markdown | 7.8 KB |
| references/precedence.md | markdown | 3.3 KB |
| references/story-bank.md | markdown | 3.6 KB |
| references/untrusted-content.md | markdown | 3.0 KB |
| references/voice-profile.md | markdown | 2.9 KB |
| references/voice-rules.md | markdown | 2.3 KB |
| scripts/check_actor_inputs.py | script | 5.8 KB |
| scripts/check_config.pyexecutable | script | 14.8 KB |
| scripts/check_frontmatter.py | script | 3.8 KB |
| scripts/check_markdown_references.py | script | 1.7 KB |
| scripts/check_no_secrets.py | script | 4.8 KB |
| scripts/post_comment.py | script | 2.9 KB |
| scripts/schedule_post.py | script | 4.4 KB |
| scripts/selftest.pyexecutable | script | 24.1 KB |
| scripts/sync_codex_marketplace.py | script | 3.1 KB |
scripts/post_comment.py
View on GitHub#!/usr/bin/env python3
"""CLI: draft + post a LinkedIn comment on any post URL.
Usage:
python scripts/post_comment.py "<POST_URL>" "<COMMENT_TEXT>" [--reaction INTEREST] [--dry-run]
Flow:
1. Parse URL to URN
2. Show preview
3. Prompt "post? yes/no"
4. On yes: react first, pause 10s, post comment
"""
from __future__ import annotations
import argparse
import os
import sys
import time
from pathlib import Path
# Make repo importable without install
sys.path.insert(0, str(Path(__file__).resolve().parents[1]))
from lib import PubloraClient, parse_linkedin_url, render_approval_card
def main() -> int:
ap = argparse.ArgumentParser(description=__doc__)
ap.add_argument("url")
ap.add_argument("message")
ap.add_argument("--reaction", default="INTEREST",
help="LIKE | PRAISE | EMPATHY | INTEREST | APPRECIATION | ENTERTAINMENT")
ap.add_argument("--dry-run", action="store_true", help="Preview only, don't post")
ap.add_argument("--reply-to", default=None,
help="Parent comment ID for threaded replies (optional)")
args = ap.parse_args()
parsed = parse_linkedin_url(args.url)
if not parsed.get("post_urn"):
print(f"✗ Could not parse URN from URL: {args.url}", file=sys.stderr)
return 2
post_urn = parsed["post_urn"]
platform_id = os.getenv("LINKEDIN_PLATFORM_ID")
if not platform_id:
print("✗ LINKEDIN_PLATFORM_ID not set in .env", file=sys.stderr)
return 2
parent_comment_urn = None
if args.reply_to:
parent_comment_urn = f"urn:li:comment:({post_urn},{args.reply_to})"
card = render_approval_card(
kind="reply" if parent_comment_urn else "comment",
preview_text=args.message,
target_url=args.url,
reaction_type=args.reaction,
extra_context={
"post_urn": post_urn,
"parent_comment": parent_comment_urn or "(top-level)",
"platform": platform_id,
},
)
print(card)
print()
if args.dry_run:
print("(dry-run — nothing posted)")
return 0
answer = input("Post? [yes/no]: ").strip().lower()
if answer not in {"yes", "y", "post"}:
print("Cancelled.")
return 0
client = PubloraClient()
try:
client.create_reaction(
post_urn=post_urn, platform_id=platform_id, reaction_type=args.reaction
)
print(f"✓ reacted {args.reaction}")
except Exception as e:
print(f"⚠ reaction failed (non-fatal): {e}")
time.sleep(10)
try:
resp = client.create_comment(
post_urn=post_urn,
message=args.message,
platform_id=platform_id,
parent_comment=parent_comment_urn,
)
print(f"✓ posted comment {resp.get('comment', {}).get('id', '?')}")
return 0
except Exception as e:
print(f"✗ comment failed: {e}")
return 1
if __name__ == "__main__":
sys.exit(main())
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |